© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120690
    Prev
    Next
    INDEX
    Explanations

    different variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ...
    -0.06
     Vivo
    -0.06
     frequently
    -0.06
     arduous
    -0.06
    othyroidism
    -0.06
     reliability
    -0.06
     ....
    -0.06
     parfois
    -0.06
     methylene
    -0.06
    reliability
    -0.06
    POSITIVE LOGITS
     يع
    0.07
     円
    0.06
    Different
    0.06
     компьютер
    0.06
    magic
    0.06
     simultaneously
    0.06
     diferente
    0.06
    适
    0.06
    different
    0.06
     zł
    0.06
    Activations Density 0.094%

    No Known Activations